Link Prediction Using Higher-Order Feature Combinations across Objects
Link Prediction Using Higher-Order Feature Combinations across Objects
复制标题
DOI：
10.1587/transinf.2019edp7266
复制
发表时间：
2020-08
期刊：
影响因子：
--
通讯作者：
Kyohei Atarashi;S. Oyama;M. Kurihara
中科院分区：
文献类型：
--
作者：
Kyohei Atarashi;S. Oyama;M. Kurihara
摘要链接预测是确定两个对象之间是否存在链接的计算问题，在机器学习和数据挖掘中非常重要。基于特征的链接预测（其中给出两个对象的特征向量）特别令人感兴趣，因为它也可以用于各种与识别相关的问题。尽管分解机和高阶分解机（HOFM）广泛用于基于特征的链接预测，但它们不仅使用跨两个对象的特征组合，还使用来自同一对象的特征组合。来自同一对象的特征组合与主要链接预测问题（例如预测身份）无关，因为使用它们会增加计算成本并降低准确性。在本文中，我们提出了仅在两个对象之间使用高阶特征组合的新颖模型。由于没有算法可以仅在两个对象之间有效计算高阶特征组合，因此我们通过利用报告的和新获得的方差分析核计算结果得出了一种算法。我们为所提出的模型提出了一种有效的坐标下降算法。我们还提高了现有 HOFM 的效率。此外，我们将提出的模型扩展到深度神经网络。实验结果证明了我们提出的模型的有效性。关键词
SUMMARY Link prediction, the computational problem of determining whether there is a link between two objects, is important in machine learning and data mining. Feature-based link prediction, in which the feature vectors of the two objects are given, is of particular interest because it can also be used for various identification-related problems. Although the factorization machine and the higher-order factorization machine (HOFM) are widely used for feature-based link prediction, they use feature combinations not only across the two objects but also from the same object. Feature combinations from the same object are irrelevant to major link prediction problems such as predicting identity because using them increases computational cost and degrades accuracy. In this paper, we present novel models that use higher-order feature combinations only across the two objects. Since there were no algorithms for e ffi ciently computing higher-order feature combinations only across two objects, we derive one by leveraging reported and newly obtained results of calculating the ANOVA kernel. We present an e ffi cient coordinate descent algorithm for proposed models. We also improve the e ff ectiveness of the existing one for the HOFM. Furthermore, we extend proposed models to a deep neural network. Experimental results demonstrated the e ff ectiveness of our proposed models. key words